© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18989
    Prev
    Next
    INDEX
    Explanations

    magnetic field and coils

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orgh
    -0.07
    å§Ķ
    -0.07
    èħ¾
    -0.07
    åĩıæ³ķ
    -0.07
    thouse
    -0.07
    丢äºĨ
    -0.07
    éĵ²éĻ¤
    -0.07
     STO
    -0.07
     Seal
    -0.07
     ************************************************************************
    -0.07
    POSITIVE LOGITS
    ç£ģ
    0.12
     magnetic
    0.11
    ç£ģåľº
    0.11
     magnet
    0.11
    èŀº
    0.11
     Magnetic
    0.10
     Magnet
    0.10
     coils
    0.10
    åĮĿ
    0.10
     wire
    0.10
    Activations Density 0.006%

    No Known Activations